使用 SDK for Python (Boto3) 的 Amazon Bedrock 运行时系统示例

使用 Bedrock 的 Converse API 向 AI21 Labs Jurassic-2 发送短信。

# Use the Conversation API to send a text message to AI21 Labs Jurassic-2.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Jurassic-2 Mid.
model_id = "ai21.j2-mid-v1"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to AI21 Labs Jurassic-2.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Jurassic-2 Mid.
model_id = "ai21.j2-mid-v1"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "prompt": prompt,
    "maxTokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["completions"][0]["data"]["text"]
print(response_text)

使用 Amazon Titan 图像生成器创建图片。

# Use the native inference API to create an image with Amazon Titan Image Generator

import base64
import boto3
import json
import os
import random

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Image Generator G1.
model_id = "amazon.titan-image-generator-v1"

# Define the image generation prompt for the model.
prompt = "A stylized picture of a cute old steampunk robot."

# Generate a random seed.
seed = random.randint(0, 2147483647)

# Format the request payload using the model's native structure.
native_request = {
    "taskType": "TEXT_IMAGE",
    "textToImageParams": {"text": prompt},
    "imageGenerationConfig": {
        "numberOfImages": 1,
        "quality": "standard",
        "cfgScale": 8.0,
        "height": 512,
        "width": 512,
        "seed": seed,
    },
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
response = client.invoke_model(modelId=model_id, body=request)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract the image data.
base64_image_data = model_response["images"][0]

# Save the generated image to a local folder.
i, output_dir = 1, "output"
if not os.path.exists(output_dir):
    os.makedirs(output_dir)
while os.path.exists(os.path.join(output_dir, f"titan_{i}.png")):
    i += 1

image_data = base64.b64decode(base64_image_data)

image_path = os.path.join(output_dir, f"titan_{i}.png")
with open(image_path, "wb") as file:
    file.write(image_data)

print(f"The generated image has been saved to {image_path}")

使用 Bedrock 的 Converse API 向 Amazon Titan Text 发送短信。

# Use the Conversation API to send a text message to Amazon Titan Text.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Bedrock 的 Converse API 向 Amazon Titan Text 发送短信，并实时处理响应流。

# Use the Conversation API to send a text message to Amazon Titan Text
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to Amazon Titan Text.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "inputText": prompt,
    "textGenerationConfig": {
        "maxTokenCount": 512,
        "temperature": 0.5,
    },
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["results"][0]["outputText"]
print(response_text)

使用 Invoke Model API 发送短信并实时处理响应流。

# Use the native inference API to send a text message to Amazon Titan Text
# and print the response stream.

import boto3
import json

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Premier.
model_id = "amazon.titan-text-premier-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "inputText": prompt,
    "textGenerationConfig": {
        "maxTokenCount": 512,
        "temperature": 0.5,
    },
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
streaming_response = client.invoke_model_with_response_stream(
    modelId=model_id, body=request
)

# Extract and print the response text in real-time.
for event in streaming_response["body"]:
    chunk = json.loads(event["chunk"]["bytes"])
    if "outputText" in chunk:
        print(chunk["outputText"], end="")

使用 Amazon Titan 文本嵌入创建您的第一个嵌入内容。

# Generate and print an embedding with Amazon Titan Text Embeddings V2.

import boto3
import json

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Titan Text Embeddings V2.
model_id = "amazon.titan-embed-text-v2:0"

# The text to convert to an embedding.
input_text = "Please recommend books with a theme similar to the movie 'Inception'."

# Create the request for the model.
native_request = {"inputText": input_text}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
response = client.invoke_model(modelId=model_id, body=request)

# Decode the model's native response body.
model_response = json.loads(response["body"].read())

# Extract and print the generated embedding and the input text token count.
embedding = model_response["embedding"]
input_token_count = model_response["inputTextTokenCount"]

print("\nYour input:")
print(input_text)
print(f"Number of input tokens: {input_token_count}")
print(f"Size of the generated embedding: {len(embedding)}")
print("Embedding:")
print(embedding)

使用 Bedrock 的 Converse API 向 Anthropic Claude 发送短信。

# Use the Conversation API to send a text message to Anthropic Claude.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Bedrock 的 Converse API 向 Anthropic Claude 发送短信并实时处理响应流。

# Use the Conversation API to send a text message to Anthropic Claude
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to Anthropic Claude.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 512,
    "temperature": 0.5,
    "messages": [
        {
            "role": "user",
            "content": [{"type": "text", "text": prompt}],
        }
    ],
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["content"][0]["text"]
print(response_text)

使用 Invoke Model API 发送短信并实时处理响应流。

# Use the native inference API to send a text message to Anthropic Claude
# and print the response stream.

import boto3
import json

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Claude 3 Haiku.
model_id = "anthropic.claude-3-haiku-20240307-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "anthropic_version": "bedrock-2023-05-31",
    "max_tokens": 512,
    "temperature": 0.5,
    "messages": [
        {
            "role": "user",
            "content": [{"type": "text", "text": prompt}],
        }
    ],
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
streaming_response = client.invoke_model_with_response_stream(
    modelId=model_id, body=request
)

# Extract and print the response text in real-time.
for event in streaming_response["body"]:
    chunk = json.loads(event["chunk"]["bytes"])
    if chunk["type"] == "content_block_delta":
        print(chunk["delta"].get("text", ""), end="")

使用 Bedrock 的 Converse API 向 Cohere Command 发送短信。

# Use the Conversation API to send a text message to Cohere Command.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Bedrock 的 Converse API 向 Cohere Command 发送短信并实时处理响应流。

# Use the Conversation API to send a text message to Cohere Command
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to Cohere Command R and R+.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "message": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["text"]
print(response_text)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to Cohere Command.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command Light.
model_id = "cohere.command-light-text-v14"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "prompt": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["generations"][0]["text"]
print(response_text)

使用 Invoke Model API 发送短信并实时处理响应流。

# Use the native inference API to send a text message to Cohere Command R and R+
# and print the response stream.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command R.
model_id = "cohere.command-r-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "message": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generations" in chunk:
            print(chunk["generations"][0]["text"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Invoke Model API 发送短信并实时处理响应流。

# Use the native inference API to send a text message to Cohere Command
# and print the response stream.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Command Light.
model_id = "cohere.command-light-text-v14"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Format the request payload using the model's native structure.
native_request = {
    "prompt": prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generations" in chunk:
            print(chunk["generations"][0]["text"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Bedrock 的 Converse API 向 Meta Llama 发送短信。

# Use the Conversation API to send a text message to Meta Llama.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Bedrock 的 Converse API 向 Meta Llama 发送短信并实时处理响应流。

# Use the Conversation API to send a text message to Meta Llama
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to Meta Llama 2.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 2 Chat 13B.
model_id = "meta.llama2-13b-chat-v1"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 2's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["generation"]
print(response_text)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to Meta Llama 3.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 3's instruction format.
formatted_prompt = f"""
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
"""

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["generation"]
print(response_text)

使用 Invoke Model API 发送短信并实时处理响应流。

# Use the native inference API to send a text message to Meta Llama 2
# and print the response stream.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 2 Chat 13B.
model_id = "meta.llama2-13b-chat-v1"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 2's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generation" in chunk:
            print(chunk["generation"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Invoke Model API 发送短信并实时处理响应流。

# Use the native inference API to send a text message to Meta Llama 3
# and print the response stream.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Llama 3 8b Instruct.
model_id = "meta.llama3-8b-instruct-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Llama 3's instruction format.
formatted_prompt = f"""
<|begin_of_text|>
<|start_header_id|>user<|end_header_id|>
{prompt}
<|eot_id|>
<|start_header_id|>assistant<|end_header_id|>
"""

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_gen_len": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "generation" in chunk:
            print(chunk["generation"], end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Bedrock 的 Converse API 向 Mistral 发送短信。

# Use the Conversation API to send a text message to Mistral.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    response = client.converse(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the response text.
    response_text = response["output"]["message"]["content"][0]["text"]
    print(response_text)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用 Bedrock 的 Converse API 向 Mistral 发送短信并实时处理响应流。

# Use the Conversation API to send a text message to Mistral
# and print the response stream.

import boto3
from botocore.exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region you want to use.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Start a conversation with the user message.
user_message = "Describe the purpose of a 'hello world' program in one line."
conversation = [
    {
        "role": "user",
        "content": [{"text": user_message}],
    }
]

try:
    # Send the message to the model, using a basic inference configuration.
    streaming_response = client.converse_stream(
        modelId=model_id,
        messages=conversation,
        inferenceConfig={"maxTokens": 512, "temperature": 0.5, "topP": 0.9},
    )

    # Extract and print the streamed response text in real-time.
    for chunk in streaming_response["stream"]:
        if "contentBlockDelta" in chunk:
            text = chunk["contentBlockDelta"]["delta"]["text"]
            print(text, end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

使用调用模型 API 发送短信。

# Use the native inference API to send a text message to Mistral.

import boto3
import json
from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Mistral's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    response = client.invoke_model(modelId=model_id, body=request)

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}'. Reason: {e}")
    exit(1)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract and print the response text.
response_text = model_response["outputs"][0]["text"]
print(response_text)

使用 Invoke Model API 发送短信并实时处理响应流。

# Use the native inference API to send a text message to Mistral
# and print the response stream.

import boto3
import json

from botocore.Exceptions import ClientError

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Mistral Large.
model_id = "mistral.mistral-large-2402-v1:0"

# Define the prompt for the model.
prompt = "Describe the purpose of a 'hello world' program in one line."

# Embed the prompt in Mistral's instruction format.
formatted_prompt = f"<s>[INST] {prompt} [/INST]"

# Format the request payload using the model's native structure.
native_request = {
    "prompt": formatted_prompt,
    "max_tokens": 512,
    "temperature": 0.5,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

try:
    # Invoke the model with the request.
    streaming_response = client.invoke_model_with_response_stream(
        modelId=model_id, body=request
    )

    # Extract and print the response text in real-time.
    for event in streaming_response["body"]:
        chunk = json.loads(event["chunk"]["bytes"])
        if "outputs" in chunk:
            print(chunk["outputs"][0].get("text"), end="")

except (ClientError, Exception) as e:
    print(f"ERROR: Can't invoke '{model_id}''. Reason: {e}")
    exit(1)

Python Foundation Model (FM) Playground 是一款 Python/FastAPI 示例应用程序，演示如何将 Amazon Bedrock 与 Python 结合使用。此示例演示 Python 开发人员可如何使用 Amazon Bedrock 来构建支持生成式人工智能的应用程序。您可以使用以下三个操场测试 Amazon Bedrock 基础模型并与之交互：

该示例还列出并显示您可以访问的基础模型及其特点。有关源代码和部署说明，请参阅中的项目GitHub。

Amazon Bedrock Serverless Pro AWS Step Functionsmpt Chaining 场景演示了如何使用 A mazon B edrock 和 Amazon Bedrock 代理来构建和编排复杂、无服务器且高度可扩展的生成人工智能应用程序。它包含以下工作示例：

有关完整的源代码以及设置和运行说明，请参阅上的完整项目GitHub。

使用 “稳定扩散” 创建图像。

# Use the native inference API to create an image with Stability.ai Stable Diffusion

import base64
import boto3
import json
import os
import random

# Create a Bedrock Runtime client in the AWS Region of your choice.
client = boto3.client("bedrock-runtime", region_name="us-east-1")

# Set the model ID, e.g., Stable Diffusion XL 1.
model_id = "stability.stable-diffusion-xl-v1"

# Define the image generation prompt for the model.
prompt = "A stylized picture of a cute old steampunk robot."

# Generate a random seed.
seed = random.randint(0, 4294967295)

# Format the request payload using the model's native structure.
native_request = {
    "text_prompts": [{"text": prompt}],
    "style_preset": "photographic",
    "seed": seed,
    "cfg_scale": 10,
    "steps": 30,
}

# Convert the native request to JSON.
request = json.dumps(native_request)

# Invoke the model with the request.
response = client.invoke_model(modelId=model_id, body=request)

# Decode the response body.
model_response = json.loads(response["body"].read())

# Extract the image data.
base64_image_data = model_response["artifacts"][0]["base64"]

# Save the generated image to a local folder.
i, output_dir = 1, "output"
if not os.path.exists(output_dir):
    os.makedirs(output_dir)
while os.path.exists(os.path.join(output_dir, f"stability_{i}.png")):
    i += 1

image_data = base64.b64decode(base64_image_data)

image_path = os.path.join(output_dir, f"stability_{i}.png")
with open(image_path, "wb") as file:
    file.write(image_data)

print(f"The generated image has been saved to {image_path}")